Super-resolution of spin configurations based on flow-based generative models

TL;DR

This paper introduces a flow-based generative model for super-resolution of spin configurations, enabling the generation of larger lattice configurations from smaller ones, reducing critical slowing down near phase transitions.

Contribution

The novel approach combines flow-based generative models with Monte Carlo simulations to efficiently generate large-scale spin configurations with accurate physical properties.

Findings

Achieved 8-fold increase in lattice size through super-resolution.

Generated large configurations with thermal averages matching traditional Monte Carlo results.

Reduced critical slowing down near the critical temperature.

Abstract

We present a super-resolution method for spin systems using a flow-based generative model that is a deep generative model with reversible neural network architecture. Starting from spin configurations on a two-dimensional square lattice, our model generates spin configurations of a larger lattice. As a flow-based generative model precisely estimates the distribution of the generated configurations, it can be combined with Monte Carlo simulation to generate large lattice configurations according to the Boltzmann distribution. Hence, the long-range correlation on a large configuration is reduced into the shorter one through the flow-based generative model. This alleviates the critical slowing down near the critical temperature. We demonstrated 8 times increased lattice size in the linear dimensions using our super-resolution scheme repeatedly. We numerically show that by performing simulations for $16\times 16$ configurations, our model can sample lattice configurations at $128\times 128$ on which the thermal average of physical quantities has good agreement with the one evaluated by the traditional Metropolis-Hasting Monte Carlo simulation.